An online capacity expansion io scheduling method based on hot data and deduplication operations

Abstract

The invention discloses an online expansion IO scheduling method based on hot data and deletion of repeated operations. The method includes the steps of: initializing the storage system; monitoring user access requests within a period of time; comparing the physical address of the user access request with the destination address of the data block to be migrated when the user access request is a write operation, If the two ranges are completely consistent, then modify the target address of the write operation; if the two ranges are partially consistent, first read the remaining missing data of the data block that needs to be migrated, and splice it into the content of the write operation , modify the address of the write operation to the target address of the data block to be migrated. This method effectively reduces the interaction between user access requests and migration requests during online expansion, improves the efficiency of online expansion, and accelerates user response time.

Description

technical field [0001] The invention relates to the field of computer network and computer storage, and is mainly applied in the HS6 online expansion scheme, in particular to an online expansion IO scheduling method based on hot data and deletion of duplicate operations. Background technique [0002] With the in-depth integration and development of network technology in all walks of life in society, enterprise data center storage systems are faced with the demand for massive data storage, so the capacity of existing storage systems cannot meet the higher requirements for capacity raised by the growing data scale. In order to increase the capacity of the data center storage system, expanding the capacity space of the existing storage system is a technology that must be adopted, that is, capacity expansion technology. In the process of storage cluster data expansion, the existing expansion schemes mainly consider how to reduce the cost of data migration during design, and seld...

AI Technical Summary

Problems solved by technology

In the process of storage cluster data expansion, the existing expansion schemes mainly consider how to reduce the overhead in the data migration process when designing, and seldom consider the impact of user access behavior on expansion

[0003] However, the user's access behavior has a great impact on the expansion process

First, intensive access behavior will increase the load on the disk; second, the contention of user access requests and migration requests on the disk head will cause a large number of random reads and writes; third, user access requests and migration requests are repeated. Write operation of data block

These reasons will lead to a reduction in the expansion efficiency of the online expansion scheme.

Images